Model save

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4187
+- Loss: 1.4175
 
 ## Model description
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0     | 0    | 1.4187          |
+| No log        | 0     | 0    | 1.4175          |
 
 
 ### Framework versions

adapter_config.json

@@ -17,8 +17,8 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
     "q_proj",
+    "v_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM"

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 0,
-    "eval_loss": 1.4187188148498535,
-    "eval_runtime": 58.7586,
+    "eval_loss": 1.4174754619598389,
+    "eval_runtime": 56.8025,
     "eval_samples": 1200,
-    "eval_samples_per_second": 20.423,
-    "eval_steps_per_second": 2.553,
-    "train_loss": 0.3546818494796753,
-    "train_runtime": 239.2844,
+    "eval_samples_per_second": 21.126,
+    "eval_steps_per_second": 2.641,
+    "train_loss": 0.354236364364624,
+    "train_runtime": 231.2263,
     "train_samples": 1200,
-    "train_samples_per_second": 5.015,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 5.19,
+    "train_steps_per_second": 0.009
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0,
-    "eval_loss": 1.4187188148498535,
-    "eval_runtime": 58.7586,
+    "eval_loss": 1.4174754619598389,
+    "eval_runtime": 56.8025,
     "eval_samples": 1200,
-    "eval_samples_per_second": 20.423,
-    "eval_steps_per_second": 2.553
+    "eval_samples_per_second": 21.126,
+    "eval_steps_per_second": 2.641
 }

runs/Nov30_17-23-01_hpc-hblab/events.out.tfevents.1701339877.hpc-hblab.1613988.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5adc632bb0c8e440e42f6bba3fe263fea0cf13d4b9e8482d2f5c1fd72b66dc2
+size 4806

runs/Nov30_17-23-01_hpc-hblab/events.out.tfevents.1701340165.hpc-hblab.1613988.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8372353c5c65ffc0a1c6c0f6fe5046f95ac8a40761e1195c458537683d62ee
+size 344

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0,
-    "train_loss": 0.3546818494796753,
-    "train_runtime": 239.2844,
+    "train_loss": 0.354236364364624,
+    "train_runtime": 231.2263,
     "train_samples": 1200,
-    "train_samples_per_second": 5.015,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 5.19,
+    "train_steps_per_second": 0.009
 }

trainer_state.json

@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 0,
-      "eval_loss": 1.418718695640564,
-      "eval_runtime": 59.2437,
-      "eval_samples_per_second": 20.255,
-      "eval_steps_per_second": 2.532,
+      "eval_loss": 1.417475938796997,
+      "eval_runtime": 56.9732,
+      "eval_samples_per_second": 21.063,
+      "eval_steps_per_second": 2.633,
       "step": 0
     },
     {
       "epoch": 0,
       "step": 0,
-      "total_flos": 1.1269869630652416e+16,
-      "train_loss": 0.3546818494796753,
-      "train_runtime": 239.2844,
-      "train_samples_per_second": 5.015,
-      "train_steps_per_second": 0.008
+      "total_flos": 1.1005732363173888e+16,
+      "train_loss": 0.354236364364624,
+      "train_runtime": 231.2263,
+      "train_samples_per_second": 5.19,
+      "train_steps_per_second": 0.009
     }
   ],
   "logging_steps": 5,
   "max_steps": 2,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.1269869630652416e+16,
+  "total_flos": 1.1005732363173888e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d11ab835e1773ef1f902c0fcbcfa5a15ea8e274293fd54cc24ad7877072741
+oid sha256:06965b9c22cec7d773224921cfda7673a0daccb60f0d8ddca7d6598d7bf5c2ca
 size 4600